Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.6568. Min Act: -0.1700
Data Index: 7421514 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.5943. Min Act: -0.1700
Data Index: 4639465 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.5318. Min Act: -0.1700
Data Index: 6836166 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.5318. Min Act: -0.1700
Data Index: 2704351 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.5005. Min Act: -0.1700
Data Index: 7313307 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.4693. Min Act: -0.1700
Data Index: 6927180 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.4693. Min Act: -0.1700
Data Index: 5713910 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.5005. Min Act: -0.1700
Data Index: 7972949 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.4693. Min Act: -0.1700
Data Index: 6790666 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.4380. Min Act: -0.1700
Data Index: 8272238 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.4068. Min Act: -0.1700
Data Index: 1056159 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.4380. Min Act: -0.1700
Data Index: 7926008 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.3755. Min Act: -0.1700
Data Index: 1522171 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.4068. Min Act: -0.1700
Data Index: 3998155 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.3755. Min Act: -0.1700
Data Index: 7071215 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.3755. Min Act: -0.1700
Data Index: 8791362 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.3755. Min Act: -0.1700
Data Index: 6468316 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.3755. Min Act: -0.1700
Data Index: 2717908 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.3755. Min Act: -0.1700
Data Index: 4325944 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6568. Min Range: -4.6568
Max Act: 4.4068. Min Act: -0.1700
Data Index: 344865 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19